#ifdef CONFIG_NFS_V4_1
static int nfs41_test_stateid(struct nfs_server *, nfs4_stateid *,
struct rpc_cred *);
- static int nfs41_free_stateid(struct nfs_server *, nfs4_stateid *,
- struct rpc_cred *);
+ static int nfs41_free_stateid(struct nfs_server *, const nfs4_stateid *,
+ struct rpc_cred *, bool);
#endif
#ifdef CONFIG_NFS_V4_SECURITY_LABEL
kunmap_atomic(start);
}
+ static void nfs4_test_and_free_stateid(struct nfs_server *server,
+ nfs4_stateid *stateid,
+ struct rpc_cred *cred)
+ {
+ const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops;
+
+ ops->test_and_free_expired(server, stateid, cred);
+ }
+
+ static void __nfs4_free_revoked_stateid(struct nfs_server *server,
+ nfs4_stateid *stateid,
+ struct rpc_cred *cred)
+ {
+ stateid->type = NFS4_REVOKED_STATEID_TYPE;
+ nfs4_test_and_free_stateid(server, stateid, cred);
+ }
+
+ static void nfs4_free_revoked_stateid(struct nfs_server *server,
+ const nfs4_stateid *stateid,
+ struct rpc_cred *cred)
+ {
+ nfs4_stateid tmp;
+
+ nfs4_stateid_copy(&tmp, stateid);
+ __nfs4_free_revoked_stateid(server, &tmp, cred);
+ }
+
static long nfs4_update_delay(long *timeout)
{
long ret;
exception->delay = 0;
exception->recovering = 0;
exception->retry = 0;
+
+ if (stateid == NULL && state != NULL)
+ stateid = &state->stateid;
+
switch(errorcode) {
case 0:
return 0;
- case -NFS4ERR_OPENMODE:
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
+ if (inode != NULL && stateid != NULL) {
+ nfs_inode_find_state_and_recover(inode,
+ stateid);
+ goto wait_on_recovery;
+ }
+ case -NFS4ERR_OPENMODE:
if (inode) {
int err;
if (ret < 0)
break;
goto wait_on_recovery;
- case -NFS4ERR_EXPIRED:
- if (state != NULL) {
- ret = nfs4_schedule_stateid_recovery(server, state);
- if (ret < 0)
- break;
- }
case -NFS4ERR_STALE_STATEID:
case -NFS4ERR_STALE_CLIENTID:
nfs4_schedule_lease_recovery(clp);
}
spin_unlock(&tbl->slot_tbl_lock);
+ slot->privileged = args->sa_privileged ? 1 : 0;
args->sa_slot = slot;
res->sr_slot = slot;
/* Check the SEQUENCE operation status */
switch (res->sr_status) {
case 0:
+ /* If previous op on slot was interrupted and we reused
+ * the seq# and got a reply from the cache, then retry
+ */
+ if (task->tk_status == -EREMOTEIO && interrupted) {
+ ++slot->seq_nr;
+ goto retry_nowait;
+ }
/* Update the slot's sequence and clientid lease timer */
slot->seq_done = 1;
clp = session->clp;
do_renew_lease(clp, res->sr_timestamp);
/* Check sequence flags */
- nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+ nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags,
+ !!slot->privileged);
nfs41_update_target_slotid(slot->table, slot, res);
break;
case 1:
}
spin_unlock(&tbl->slot_tbl_lock);
+ slot->privileged = args->sa_privileged ? 1 : 0;
args->sa_slot = slot;
dprintk("<-- %s slotid=%u seqid=%u\n", __func__,
nfs4_state_set_mode_locked(state, state->state | fmode);
}
+ #ifdef CONFIG_NFS_V4_1
+ static bool nfs_open_stateid_recover_openmode(struct nfs4_state *state)
+ {
+ if (state->n_rdonly && !test_bit(NFS_O_RDONLY_STATE, &state->flags))
+ return true;
+ if (state->n_wronly && !test_bit(NFS_O_WRONLY_STATE, &state->flags))
+ return true;
+ if (state->n_rdwr && !test_bit(NFS_O_RDWR_STATE, &state->flags))
+ return true;
+ return false;
+ }
+ #endif /* CONFIG_NFS_V4_1 */
+
static void nfs_test_and_clear_all_open_stateid(struct nfs4_state *state)
{
struct nfs_client *clp = state->owner->so_server->nfs_client;
}
static bool nfs_need_update_open_stateid(struct nfs4_state *state,
- nfs4_stateid *stateid)
+ const nfs4_stateid *stateid, nfs4_stateid *freeme)
{
if (test_and_set_bit(NFS_OPEN_STATE, &state->flags) == 0)
return true;
if (!nfs4_stateid_match_other(stateid, &state->open_stateid)) {
+ nfs4_stateid_copy(freeme, &state->open_stateid);
nfs_test_and_clear_all_open_stateid(state);
return true;
}
nfs4_schedule_state_manager(state->owner->so_server->nfs_client);
}
- static void nfs_set_open_stateid_locked(struct nfs4_state *state, nfs4_stateid *stateid, fmode_t fmode)
+ static void nfs_set_open_stateid_locked(struct nfs4_state *state,
+ const nfs4_stateid *stateid, fmode_t fmode,
+ nfs4_stateid *freeme)
{
switch (fmode) {
case FMODE_READ:
case FMODE_READ|FMODE_WRITE:
set_bit(NFS_O_RDWR_STATE, &state->flags);
}
- if (!nfs_need_update_open_stateid(state, stateid))
+ if (!nfs_need_update_open_stateid(state, stateid, freeme))
return;
if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0)
nfs4_stateid_copy(&state->stateid, stateid);
nfs4_stateid_copy(&state->open_stateid, stateid);
}
- static void __update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, const nfs4_stateid *deleg_stateid, fmode_t fmode)
+ static void __update_open_stateid(struct nfs4_state *state,
+ const nfs4_stateid *open_stateid,
+ const nfs4_stateid *deleg_stateid,
+ fmode_t fmode,
+ nfs4_stateid *freeme)
{
/*
* Protect the call to nfs4_state_set_mode_locked and
set_bit(NFS_DELEGATED_STATE, &state->flags);
}
if (open_stateid != NULL)
- nfs_set_open_stateid_locked(state, open_stateid, fmode);
+ nfs_set_open_stateid_locked(state, open_stateid, fmode, freeme);
write_sequnlock(&state->seqlock);
update_open_stateflags(state, fmode);
spin_unlock(&state->owner->so_lock);
}
- static int update_open_stateid(struct nfs4_state *state, nfs4_stateid *open_stateid, nfs4_stateid *delegation, fmode_t fmode)
+ static int update_open_stateid(struct nfs4_state *state,
+ const nfs4_stateid *open_stateid,
+ const nfs4_stateid *delegation,
+ fmode_t fmode)
{
+ struct nfs_server *server = NFS_SERVER(state->inode);
+ struct nfs_client *clp = server->nfs_client;
struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs_delegation *deleg_cur;
+ nfs4_stateid freeme = {0};
int ret = 0;
fmode &= (FMODE_READ|FMODE_WRITE);
goto no_delegation_unlock;
nfs_mark_delegation_referenced(deleg_cur);
- __update_open_stateid(state, open_stateid, &deleg_cur->stateid, fmode);
+ __update_open_stateid(state, open_stateid, &deleg_cur->stateid,
+ fmode, &freeme);
ret = 1;
no_delegation_unlock:
spin_unlock(&deleg_cur->lock);
rcu_read_unlock();
if (!ret && open_stateid != NULL) {
- __update_open_stateid(state, open_stateid, NULL, fmode);
+ __update_open_stateid(state, open_stateid, NULL, fmode, &freeme);
ret = 1;
}
if (test_bit(NFS_STATE_RECLAIM_NOGRACE, &state->flags))
- nfs4_schedule_state_manager(state->owner->so_server->nfs_client);
+ nfs4_schedule_state_manager(clp);
+ if (freeme.type != 0)
+ nfs4_test_and_free_stateid(server, &freeme,
+ state->owner->so_cred);
return ret;
}
case -NFS4ERR_STALE_CLIENTID:
case -NFS4ERR_STALE_STATEID:
set_bit(NFS_DELEGATED_STATE, &state->flags);
- case -NFS4ERR_EXPIRED:
/* Don't recall a delegation if it was lost */
nfs4_schedule_lease_recovery(server->nfs_client);
return -EAGAIN;
return -EAGAIN;
case -NFS4ERR_DELEG_REVOKED:
case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
case -NFS4ERR_OPENMODE:
nfs_inode_find_state_and_recover(state->inode,
return ret;
}
- static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state)
+ static void nfs_finish_clear_delegation_stateid(struct nfs4_state *state,
+ const nfs4_stateid *stateid)
{
- nfs_remove_bad_delegation(state->inode);
+ nfs_remove_bad_delegation(state->inode, stateid);
write_seqlock(&state->seqlock);
nfs4_stateid_copy(&state->stateid, &state->open_stateid);
write_sequnlock(&state->seqlock);
static void nfs40_clear_delegation_stateid(struct nfs4_state *state)
{
if (rcu_access_pointer(NFS_I(state->inode)->delegation) != NULL)
- nfs_finish_clear_delegation_stateid(state);
+ nfs_finish_clear_delegation_stateid(state, NULL);
}
static int nfs40_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
return nfs4_open_expired(sp, state);
}
+ static int nfs40_test_and_free_expired_stateid(struct nfs_server *server,
+ nfs4_stateid *stateid,
+ struct rpc_cred *cred)
+ {
+ return -NFS4ERR_BAD_STATEID;
+ }
+
#if defined(CONFIG_NFS_V4_1)
+ static int nfs41_test_and_free_expired_stateid(struct nfs_server *server,
+ nfs4_stateid *stateid,
+ struct rpc_cred *cred)
+ {
+ int status;
+
+ switch (stateid->type) {
+ default:
+ break;
+ case NFS4_INVALID_STATEID_TYPE:
+ case NFS4_SPECIAL_STATEID_TYPE:
+ return -NFS4ERR_BAD_STATEID;
+ case NFS4_REVOKED_STATEID_TYPE:
+ goto out_free;
+ }
+
+ status = nfs41_test_stateid(server, stateid, cred);
+ switch (status) {
+ case -NFS4ERR_EXPIRED:
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_DELEG_REVOKED:
+ break;
+ default:
+ return status;
+ }
+ out_free:
+ /* Ack the revoked state to the server */
+ nfs41_free_stateid(server, stateid, cred, true);
+ return -NFS4ERR_EXPIRED;
+ }
+
static void nfs41_check_delegation_stateid(struct nfs4_state *state)
{
struct nfs_server *server = NFS_SERVER(state->inode);
}
nfs4_stateid_copy(&stateid, &delegation->stateid);
+ if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
+ rcu_read_unlock();
+ nfs_finish_clear_delegation_stateid(state, &stateid);
+ return;
+ }
+
+ if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) {
+ rcu_read_unlock();
+ return;
+ }
+
cred = get_rpccred(delegation->cred);
rcu_read_unlock();
- status = nfs41_test_stateid(server, &stateid, cred);
+ status = nfs41_test_and_free_expired_stateid(server, &stateid, cred);
trace_nfs4_test_delegation_stateid(state, NULL, status);
-
- if (status != NFS_OK) {
- /* Free the stateid unless the server explicitly
- * informs us the stateid is unrecognized. */
- if (status != -NFS4ERR_BAD_STATEID)
- nfs41_free_stateid(server, &stateid, cred);
- nfs_finish_clear_delegation_stateid(state);
- }
+ if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID)
+ nfs_finish_clear_delegation_stateid(state, &stateid);
put_rpccred(cred);
}
+ /**
+ * nfs41_check_expired_locks - possibly free a lock stateid
+ *
+ * @state: NFSv4 state for an inode
+ *
+ * Returns NFS_OK if recovery for this stateid is now finished.
+ * Otherwise a negative NFS4ERR value is returned.
+ */
+ static int nfs41_check_expired_locks(struct nfs4_state *state)
+ {
+ int status, ret = NFS_OK;
+ struct nfs4_lock_state *lsp;
+ struct nfs_server *server = NFS_SERVER(state->inode);
+
+ if (!test_bit(LK_STATE_IN_USE, &state->flags))
+ goto out;
+ list_for_each_entry(lsp, &state->lock_states, ls_locks) {
+ if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
+ struct rpc_cred *cred = lsp->ls_state->owner->so_cred;
+
+ status = nfs41_test_and_free_expired_stateid(server,
+ &lsp->ls_stateid,
+ cred);
+ trace_nfs4_test_lock_stateid(state, lsp, status);
+ if (status == -NFS4ERR_EXPIRED ||
+ status == -NFS4ERR_BAD_STATEID) {
+ clear_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
+ lsp->ls_stateid.type = NFS4_INVALID_STATEID_TYPE;
+ if (!recover_lost_locks)
+ set_bit(NFS_LOCK_LOST, &lsp->ls_flags);
+ } else if (status != NFS_OK) {
+ ret = status;
+ break;
+ }
+ }
+ };
+ out:
+ return ret;
+ }
+
/**
* nfs41_check_open_stateid - possibly free an open stateid
*
struct rpc_cred *cred = state->owner->so_cred;
int status;
- /* If a state reset has been done, test_stateid is unneeded */
- if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) &&
- (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) &&
- (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0))
+ if (test_bit(NFS_OPEN_STATE, &state->flags) == 0) {
+ if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) {
+ if (nfs4_have_delegation(state->inode, state->state))
+ return NFS_OK;
+ return -NFS4ERR_OPENMODE;
+ }
return -NFS4ERR_BAD_STATEID;
-
- status = nfs41_test_stateid(server, stateid, cred);
+ }
+ status = nfs41_test_and_free_expired_stateid(server, stateid, cred);
trace_nfs4_test_open_stateid(state, NULL, status);
- if (status != NFS_OK) {
- /* Free the stateid unless the server explicitly
- * informs us the stateid is unrecognized. */
- if (status != -NFS4ERR_BAD_STATEID)
- nfs41_free_stateid(server, stateid, cred);
-
+ if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) {
clear_bit(NFS_O_RDONLY_STATE, &state->flags);
clear_bit(NFS_O_WRONLY_STATE, &state->flags);
clear_bit(NFS_O_RDWR_STATE, &state->flags);
clear_bit(NFS_OPEN_STATE, &state->flags);
+ stateid->type = NFS4_INVALID_STATEID_TYPE;
}
- return status;
+ if (status != NFS_OK)
+ return status;
+ if (nfs_open_stateid_recover_openmode(state))
+ return -NFS4ERR_OPENMODE;
+ return NFS_OK;
}
static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state)
int status;
nfs41_check_delegation_stateid(state);
+ status = nfs41_check_expired_locks(state);
+ if (status != NFS_OK)
+ return status;
status = nfs41_check_open_stateid(state);
if (status != NFS_OK)
status = nfs4_open_expired(sp, state);
goto out;
if (server->caps & NFS_CAP_POSIX_LOCK)
set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
+ if (opendata->o_res.rflags & NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK)
+ set_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags);
dentry = opendata->dentry;
if (d_really_is_negative(dentry)) {
break;
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_STALE_STATEID:
+ case -NFS4ERR_EXPIRED:
+ nfs4_free_revoked_stateid(server,
+ &calldata->arg.stateid,
+ task->tk_msg.rpc_cred);
case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_BAD_STATEID:
- case -NFS4ERR_EXPIRED:
if (!nfs4_stateid_match(&calldata->arg.stateid,
&state->open_stateid)) {
rpc_restart_call_prepare(task);
if (error == 0) {
/* block layout checks this! */
server->pnfs_blksize = fsinfo->blksize;
- set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype);
+ set_pnfs_layoutdriver(server, fhandle, fsinfo);
}
return error;
return false;
}
- void __nfs4_read_done_cb(struct nfs_pgio_header *hdr)
- {
- nfs_invalidate_atime(hdr->inode);
- }
-
static int nfs4_read_done_cb(struct rpc_task *task, struct nfs_pgio_header *hdr)
{
struct nfs_server *server = NFS_SERVER(hdr->inode);
trace_nfs4_read(hdr, task->tk_status);
- if (nfs4_async_handle_error(task, server,
- hdr->args.context->state,
- NULL) == -EAGAIN) {
- rpc_restart_call_prepare(task);
- return -EAGAIN;
+ if (task->tk_status < 0) {
+ struct nfs4_exception exception = {
+ .inode = hdr->inode,
+ .state = hdr->args.context->state,
+ .stateid = &hdr->args.stateid,
+ };
+ task->tk_status = nfs4_async_handle_exception(task,
+ server, task->tk_status, &exception);
+ if (exception.retry) {
+ rpc_restart_call_prepare(task);
+ return -EAGAIN;
+ }
}
- __nfs4_read_done_cb(hdr);
if (task->tk_status > 0)
renew_lease(server, hdr->timestamp);
return 0;
return -EAGAIN;
if (nfs4_read_stateid_changed(task, &hdr->args))
return -EAGAIN;
+ if (task->tk_status > 0)
+ nfs_invalidate_atime(hdr->inode);
return hdr->pgio_done_cb ? hdr->pgio_done_cb(task, hdr) :
nfs4_read_done_cb(task, hdr);
}
struct inode *inode = hdr->inode;
trace_nfs4_write(hdr, task->tk_status);
- if (nfs4_async_handle_error(task, NFS_SERVER(inode),
- hdr->args.context->state,
- NULL) == -EAGAIN) {
- rpc_restart_call_prepare(task);
- return -EAGAIN;
+ if (task->tk_status < 0) {
+ struct nfs4_exception exception = {
+ .inode = hdr->inode,
+ .state = hdr->args.context->state,
+ .stateid = &hdr->args.stateid,
+ };
+ task->tk_status = nfs4_async_handle_exception(task,
+ NFS_SERVER(inode), task->tk_status,
+ &exception);
+ if (exception.retry) {
+ rpc_restart_call_prepare(task);
+ return -EAGAIN;
+ }
}
if (task->tk_status >= 0) {
renew_lease(NFS_SERVER(inode), hdr->timestamp);
if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) {
/* An impossible timestamp guarantees this value
* will never match a generated boot time. */
- verf[0] = 0;
- verf[1] = cpu_to_be32(NSEC_PER_SEC + 1);
+ verf[0] = cpu_to_be32(U32_MAX);
+ verf[1] = cpu_to_be32(U32_MAX);
} else {
struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id);
- verf[0] = cpu_to_be32(nn->boot_time.tv_sec);
- verf[1] = cpu_to_be32(nn->boot_time.tv_nsec);
+ u64 ns = ktime_to_ns(nn->boot_time);
+
+ verf[0] = cpu_to_be32(ns >> 32);
+ verf[1] = cpu_to_be32(ns);
}
memcpy(bootverf->data, verf, sizeof(bootverf->data));
}
renew_lease(data->res.server, data->timestamp);
case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_EXPIRED:
+ nfs4_free_revoked_stateid(data->res.server,
+ data->args.stateid,
+ task->tk_msg.rpc_cred);
case -NFS4ERR_BAD_STATEID:
case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_EXPIRED:
task->tk_status = 0;
if (data->roc)
pnfs_roc_set_barrier(data->inode, data->roc_barrier);
return err;
}
- #define NFS4_LOCK_MINTIMEOUT (1 * HZ)
- #define NFS4_LOCK_MAXTIMEOUT (30 * HZ)
-
- /*
- * sleep, with exponential backoff, and retry the LOCK operation.
- */
- static unsigned long
- nfs4_set_lock_task_retry(unsigned long timeout)
- {
- freezable_schedule_timeout_killable_unsafe(timeout);
- timeout <<= 1;
- if (timeout > NFS4_LOCK_MAXTIMEOUT)
- return NFS4_LOCK_MAXTIMEOUT;
- return timeout;
- }
-
static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock *request)
{
struct inode *inode = state->inode;
return err;
}
- static int do_vfs_lock(struct inode *inode, struct file_lock *fl)
- {
- return locks_lock_inode_wait(inode, fl);
- }
-
struct nfs4_unlockdata {
struct nfs_locku_args arg;
struct nfs_locku_res res;
switch (task->tk_status) {
case 0:
renew_lease(calldata->server, calldata->timestamp);
- do_vfs_lock(calldata->lsp->ls_state->inode, &calldata->fl);
+ locks_lock_inode_wait(calldata->lsp->ls_state->inode, &calldata->fl);
if (nfs4_update_lock_stateid(calldata->lsp,
&calldata->res.stateid))
break;
+ case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_EXPIRED:
+ nfs4_free_revoked_stateid(calldata->server,
+ &calldata->arg.stateid,
+ task->tk_msg.rpc_cred);
case -NFS4ERR_BAD_STATEID:
case -NFS4ERR_OLD_STATEID:
case -NFS4ERR_STALE_STATEID:
- case -NFS4ERR_EXPIRED:
if (!nfs4_stateid_match(&calldata->arg.stateid,
&calldata->lsp->ls_stateid))
rpc_restart_call_prepare(task);
mutex_lock(&sp->so_delegreturn_mutex);
/* Exclude nfs4_reclaim_open_stateid() - note nesting! */
down_read(&nfsi->rwsem);
- if (do_vfs_lock(inode, request) == -ENOENT) {
+ if (locks_lock_inode_wait(inode, request) == -ENOENT) {
up_read(&nfsi->rwsem);
mutex_unlock(&sp->so_delegreturn_mutex);
goto out;
data->timestamp);
if (data->arg.new_lock) {
data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
- if (do_vfs_lock(lsp->ls_state->inode, &data->fl) < 0) {
+ if (locks_lock_inode_wait(lsp->ls_state->inode, &data->fl) < 0) {
rpc_restart_call_prepare(task);
break;
}
{
switch (error) {
case -NFS4ERR_ADMIN_REVOKED:
+ case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
if (new_lock_owner != 0 ||
break;
case -NFS4ERR_STALE_STATEID:
lsp->ls_seqid.flags &= ~NFS_SEQID_CONFIRMED;
- case -NFS4ERR_EXPIRED:
nfs4_schedule_lease_recovery(server->nfs_client);
};
}
}
#if defined(CONFIG_NFS_V4_1)
- /**
- * nfs41_check_expired_locks - possibly free a lock stateid
- *
- * @state: NFSv4 state for an inode
- *
- * Returns NFS_OK if recovery for this stateid is now finished.
- * Otherwise a negative NFS4ERR value is returned.
- */
- static int nfs41_check_expired_locks(struct nfs4_state *state)
- {
- int status, ret = -NFS4ERR_BAD_STATEID;
- struct nfs4_lock_state *lsp;
- struct nfs_server *server = NFS_SERVER(state->inode);
-
- list_for_each_entry(lsp, &state->lock_states, ls_locks) {
- if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
- struct rpc_cred *cred = lsp->ls_state->owner->so_cred;
-
- status = nfs41_test_stateid(server,
- &lsp->ls_stateid,
- cred);
- trace_nfs4_test_lock_stateid(state, lsp, status);
- if (status != NFS_OK) {
- /* Free the stateid unless the server
- * informs us the stateid is unrecognized. */
- if (status != -NFS4ERR_BAD_STATEID)
- nfs41_free_stateid(server,
- &lsp->ls_stateid,
- cred);
- clear_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags);
- ret = status;
- }
- }
- };
-
- return ret;
- }
-
static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *request)
{
- int status = NFS_OK;
+ struct nfs4_lock_state *lsp;
+ int status;
- if (test_bit(LK_STATE_IN_USE, &state->flags))
- status = nfs41_check_expired_locks(state);
- if (status != NFS_OK)
- status = nfs4_lock_expired(state, request);
+ status = nfs4_set_lock_state(state, request);
+ if (status != 0)
+ return status;
+ lsp = request->fl_u.nfs4_fl.owner;
+ if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) ||
+ test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
+ return 0;
+ status = nfs4_lock_expired(state, request);
return status;
}
#endif
struct nfs_inode *nfsi = NFS_I(state->inode);
struct nfs4_state_owner *sp = state->owner;
unsigned char fl_flags = request->fl_flags;
- int status = -ENOLCK;
+ int status;
- if ((fl_flags & FL_POSIX) &&
- !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
- goto out;
- /* Is this a delegated open? */
- status = nfs4_set_lock_state(state, request);
- if (status != 0)
- goto out;
request->fl_flags |= FL_ACCESS;
- status = do_vfs_lock(state->inode, request);
+ status = locks_lock_inode_wait(state->inode, request);
if (status < 0)
goto out;
mutex_lock(&sp->so_delegreturn_mutex);
/* Yes: cache locks! */
/* ...but avoid races with delegation recall... */
request->fl_flags = fl_flags & ~FL_SLEEP;
- status = do_vfs_lock(state->inode, request);
+ status = locks_lock_inode_wait(state->inode, request);
up_read(&nfsi->rwsem);
mutex_unlock(&sp->so_delegreturn_mutex);
goto out;
return err;
}
+ #define NFS4_LOCK_MINTIMEOUT (1 * HZ)
+ #define NFS4_LOCK_MAXTIMEOUT (30 * HZ)
+
+ static int
+ nfs4_retry_setlk_simple(struct nfs4_state *state, int cmd,
+ struct file_lock *request)
+ {
+ int status = -ERESTARTSYS;
+ unsigned long timeout = NFS4_LOCK_MINTIMEOUT;
+
+ while(!signalled()) {
+ status = nfs4_proc_setlk(state, cmd, request);
+ if ((status != -EAGAIN) || IS_SETLK(cmd))
+ break;
+ freezable_schedule_timeout_interruptible(timeout);
+ timeout *= 2;
+ timeout = min_t(unsigned long, NFS4_LOCK_MAXTIMEOUT, timeout);
+ status = -ERESTARTSYS;
+ }
+ return status;
+ }
+
+ #ifdef CONFIG_NFS_V4_1
+ struct nfs4_lock_waiter {
+ struct task_struct *task;
+ struct inode *inode;
+ struct nfs_lowner *owner;
+ bool notified;
+ };
+
+ static int
+ nfs4_wake_lock_waiter(wait_queue_t *wait, unsigned int mode, int flags, void *key)
+ {
+ int ret;
+ struct cb_notify_lock_args *cbnl = key;
+ struct nfs4_lock_waiter *waiter = wait->private;
+ struct nfs_lowner *lowner = &cbnl->cbnl_owner,
+ *wowner = waiter->owner;
+
+ /* Only wake if the callback was for the same owner */
+ if (lowner->clientid != wowner->clientid ||
+ lowner->id != wowner->id ||
+ lowner->s_dev != wowner->s_dev)
+ return 0;
+
+ /* Make sure it's for the right inode */
+ if (nfs_compare_fh(NFS_FH(waiter->inode), &cbnl->cbnl_fh))
+ return 0;
+
+ waiter->notified = true;
+
+ /* override "private" so we can use default_wake_function */
+ wait->private = waiter->task;
+ ret = autoremove_wake_function(wait, mode, flags, key);
+ wait->private = waiter;
+ return ret;
+ }
+
+ static int
+ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
+ {
+ int status = -ERESTARTSYS;
+ unsigned long flags;
+ struct nfs4_lock_state *lsp = request->fl_u.nfs4_fl.owner;
+ struct nfs_server *server = NFS_SERVER(state->inode);
+ struct nfs_client *clp = server->nfs_client;
+ wait_queue_head_t *q = &clp->cl_lock_waitq;
+ struct nfs_lowner owner = { .clientid = clp->cl_clientid,
+ .id = lsp->ls_seqid.owner_id,
+ .s_dev = server->s_dev };
+ struct nfs4_lock_waiter waiter = { .task = current,
+ .inode = state->inode,
+ .owner = &owner,
+ .notified = false };
+ wait_queue_t wait;
+
+ /* Don't bother with waitqueue if we don't expect a callback */
+ if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags))
+ return nfs4_retry_setlk_simple(state, cmd, request);
+
+ init_wait(&wait);
+ wait.private = &waiter;
+ wait.func = nfs4_wake_lock_waiter;
+ add_wait_queue(q, &wait);
+
+ while(!signalled()) {
+ status = nfs4_proc_setlk(state, cmd, request);
+ if ((status != -EAGAIN) || IS_SETLK(cmd))
+ break;
+
+ status = -ERESTARTSYS;
+ spin_lock_irqsave(&q->lock, flags);
+ if (waiter.notified) {
+ spin_unlock_irqrestore(&q->lock, flags);
+ continue;
+ }
+ set_current_state(TASK_INTERRUPTIBLE);
+ spin_unlock_irqrestore(&q->lock, flags);
+
+ freezable_schedule_timeout_interruptible(NFS4_LOCK_MAXTIMEOUT);
+ }
+
+ finish_wait(q, &wait);
+ return status;
+ }
+ #else /* !CONFIG_NFS_V4_1 */
+ static inline int
+ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
+ {
+ return nfs4_retry_setlk_simple(state, cmd, request);
+ }
+ #endif
+
static int
nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
{
struct nfs_open_context *ctx;
struct nfs4_state *state;
- unsigned long timeout = NFS4_LOCK_MINTIMEOUT;
int status;
/* verify open state */
if (state == NULL)
return -ENOLCK;
+
+ if ((request->fl_flags & FL_POSIX) &&
+ !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
+ return -ENOLCK;
+
/*
* Don't rely on the VFS having checked the file open mode,
* since it won't do this for flock() locks.
return -EBADF;
}
- do {
- status = nfs4_proc_setlk(state, cmd, request);
- if ((status != -EAGAIN) || IS_SETLK(cmd))
- break;
- timeout = nfs4_set_lock_task_retry(timeout);
- status = -ERESTARTSYS;
- if (signalled())
- break;
- } while(status < 0);
- return status;
+ status = nfs4_set_lock_state(state, request);
+ if (status != 0)
+ return status;
+
+ return nfs4_retry_setlk(state, cmd, request);
}
int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid)
return 0;
}
+ struct nfs41_exchange_id_data {
+ struct nfs41_exchange_id_res res;
+ struct nfs41_exchange_id_args args;
+ struct rpc_xprt *xprt;
+ int rpc_status;
+ };
+
+ static void nfs4_exchange_id_done(struct rpc_task *task, void *data)
+ {
+ struct nfs41_exchange_id_data *cdata =
+ (struct nfs41_exchange_id_data *)data;
+ struct nfs_client *clp = cdata->args.client;
+ int status = task->tk_status;
+
+ trace_nfs4_exchange_id(clp, status);
+
+ if (status == 0)
+ status = nfs4_check_cl_exchange_flags(cdata->res.flags);
+
+ if (cdata->xprt && status == 0) {
+ status = nfs4_detect_session_trunking(clp, &cdata->res,
+ cdata->xprt);
+ goto out;
+ }
+
+ if (status == 0)
+ status = nfs4_sp4_select_mode(clp, &cdata->res.state_protect);
+
+ if (status == 0) {
+ clp->cl_clientid = cdata->res.clientid;
+ clp->cl_exchange_flags = cdata->res.flags;
+ /* Client ID is not confirmed */
+ if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R)) {
+ clear_bit(NFS4_SESSION_ESTABLISHED,
+ &clp->cl_session->session_state);
+ clp->cl_seqid = cdata->res.seqid;
+ }
+
+ kfree(clp->cl_serverowner);
+ clp->cl_serverowner = cdata->res.server_owner;
+ cdata->res.server_owner = NULL;
+
+ /* use the most recent implementation id */
+ kfree(clp->cl_implid);
+ clp->cl_implid = cdata->res.impl_id;
+ cdata->res.impl_id = NULL;
+
+ if (clp->cl_serverscope != NULL &&
+ !nfs41_same_server_scope(clp->cl_serverscope,
+ cdata->res.server_scope)) {
+ dprintk("%s: server_scope mismatch detected\n",
+ __func__);
+ set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
+ kfree(clp->cl_serverscope);
+ clp->cl_serverscope = NULL;
+ }
+
+ if (clp->cl_serverscope == NULL) {
+ clp->cl_serverscope = cdata->res.server_scope;
+ cdata->res.server_scope = NULL;
+ }
+ /* Save the EXCHANGE_ID verifier session trunk tests */
+ memcpy(clp->cl_confirm.data, cdata->args.verifier->data,
+ sizeof(clp->cl_confirm.data));
+ }
+ out:
+ cdata->rpc_status = status;
+ return;
+ }
+
+ static void nfs4_exchange_id_release(void *data)
+ {
+ struct nfs41_exchange_id_data *cdata =
+ (struct nfs41_exchange_id_data *)data;
+
+ nfs_put_client(cdata->args.client);
+ if (cdata->xprt) {
+ xprt_put(cdata->xprt);
+ rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient);
+ }
+ kfree(cdata->res.impl_id);
+ kfree(cdata->res.server_scope);
+ kfree(cdata->res.server_owner);
+ kfree(cdata);
+ }
+
+ static const struct rpc_call_ops nfs4_exchange_id_call_ops = {
+ .rpc_call_done = nfs4_exchange_id_done,
+ .rpc_release = nfs4_exchange_id_release,
+ };
+
/*
* _nfs4_proc_exchange_id()
*
* Wrapper for EXCHANGE_ID operation.
*/
static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
- u32 sp4_how)
+ u32 sp4_how, struct rpc_xprt *xprt)
{
nfs4_verifier verifier;
- struct nfs41_exchange_id_args args = {
- .verifier = &verifier,
- .client = clp,
- #ifdef CONFIG_NFS_V4_1_MIGRATION
- .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
- EXCHGID4_FLAG_BIND_PRINC_STATEID |
- EXCHGID4_FLAG_SUPP_MOVED_MIGR,
- #else
- .flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
- EXCHGID4_FLAG_BIND_PRINC_STATEID,
- #endif
- };
- struct nfs41_exchange_id_res res = {
- 0
- };
- int status;
struct rpc_message msg = {
.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_EXCHANGE_ID],
- .rpc_argp = &args,
- .rpc_resp = &res,
.rpc_cred = cred,
};
+ struct rpc_task_setup task_setup_data = {
+ .rpc_client = clp->cl_rpcclient,
+ .callback_ops = &nfs4_exchange_id_call_ops,
+ .rpc_message = &msg,
+ .flags = RPC_TASK_ASYNC | RPC_TASK_TIMEOUT,
+ };
+ struct nfs41_exchange_id_data *calldata;
+ struct rpc_task *task;
+ int status = -EIO;
+
+ if (!atomic_inc_not_zero(&clp->cl_count))
+ goto out;
+
+ status = -ENOMEM;
+ calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
+ if (!calldata)
+ goto out;
- nfs4_init_boot_verifier(clp, &verifier);
+ if (!xprt)
+ nfs4_init_boot_verifier(clp, &verifier);
status = nfs4_init_uniform_client_string(clp);
if (status)
- goto out;
+ goto out_calldata;
dprintk("NFS call exchange_id auth=%s, '%s'\n",
clp->cl_rpcclient->cl_auth->au_ops->au_name,
clp->cl_owner_id);
- res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
- GFP_NOFS);
- if (unlikely(res.server_owner == NULL)) {
- status = -ENOMEM;
- goto out;
- }
+ calldata->res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
+ GFP_NOFS);
+ status = -ENOMEM;
+ if (unlikely(calldata->res.server_owner == NULL))
+ goto out_calldata;
- res.server_scope = kzalloc(sizeof(struct nfs41_server_scope),
+ calldata->res.server_scope = kzalloc(sizeof(struct nfs41_server_scope),
GFP_NOFS);
- if (unlikely(res.server_scope == NULL)) {
- status = -ENOMEM;
+ if (unlikely(calldata->res.server_scope == NULL))
goto out_server_owner;
- }
- res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_NOFS);
- if (unlikely(res.impl_id == NULL)) {
- status = -ENOMEM;
+ calldata->res.impl_id = kzalloc(sizeof(struct nfs41_impl_id), GFP_NOFS);
+ if (unlikely(calldata->res.impl_id == NULL))
goto out_server_scope;
- }
switch (sp4_how) {
case SP4_NONE:
- args.state_protect.how = SP4_NONE;
+ calldata->args.state_protect.how = SP4_NONE;
break;
case SP4_MACH_CRED:
- args.state_protect = nfs4_sp4_mach_cred_request;
+ calldata->args.state_protect = nfs4_sp4_mach_cred_request;
break;
default:
status = -EINVAL;
goto out_impl_id;
}
+ if (xprt) {
+ calldata->xprt = xprt;
+ task_setup_data.rpc_xprt = xprt;
+ task_setup_data.flags =
+ RPC_TASK_SOFT|RPC_TASK_SOFTCONN|RPC_TASK_ASYNC;
+ calldata->args.verifier = &clp->cl_confirm;
+ } else {
+ calldata->args.verifier = &verifier;
+ }
+ calldata->args.client = clp;
+ #ifdef CONFIG_NFS_V4_1_MIGRATION
+ calldata->args.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
+ EXCHGID4_FLAG_BIND_PRINC_STATEID |
+ EXCHGID4_FLAG_SUPP_MOVED_MIGR,
+ #else
+ calldata->args.flags = EXCHGID4_FLAG_SUPP_MOVED_REFER |
+ EXCHGID4_FLAG_BIND_PRINC_STATEID,
+ #endif
+ msg.rpc_argp = &calldata->args;
+ msg.rpc_resp = &calldata->res;
+ task_setup_data.callback_data = calldata;
- status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
- trace_nfs4_exchange_id(clp, status);
- if (status == 0)
- status = nfs4_check_cl_exchange_flags(res.flags);
-
- if (status == 0)
- status = nfs4_sp4_select_mode(clp, &res.state_protect);
-
- if (status == 0) {
- clp->cl_clientid = res.clientid;
- clp->cl_exchange_flags = res.flags;
- /* Client ID is not confirmed */
- if (!(res.flags & EXCHGID4_FLAG_CONFIRMED_R)) {
- clear_bit(NFS4_SESSION_ESTABLISHED,
- &clp->cl_session->session_state);
- clp->cl_seqid = res.seqid;
- }
-
- kfree(clp->cl_serverowner);
- clp->cl_serverowner = res.server_owner;
- res.server_owner = NULL;
-
- /* use the most recent implementation id */
- kfree(clp->cl_implid);
- clp->cl_implid = res.impl_id;
- res.impl_id = NULL;
-
- if (clp->cl_serverscope != NULL &&
- !nfs41_same_server_scope(clp->cl_serverscope,
- res.server_scope)) {
- dprintk("%s: server_scope mismatch detected\n",
- __func__);
- set_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state);
- kfree(clp->cl_serverscope);
- clp->cl_serverscope = NULL;
- }
-
- if (clp->cl_serverscope == NULL) {
- clp->cl_serverscope = res.server_scope;
- res.server_scope = NULL;
- }
+ task = rpc_run_task(&task_setup_data);
+ if (IS_ERR(task)) {
+ status = PTR_ERR(task);
+ goto out_impl_id;
}
- out_impl_id:
- kfree(res.impl_id);
- out_server_scope:
- kfree(res.server_scope);
- out_server_owner:
- kfree(res.server_owner);
+ if (!xprt) {
+ status = rpc_wait_for_completion_task(task);
+ if (!status)
+ status = calldata->rpc_status;
+ } else /* session trunking test */
+ status = calldata->rpc_status;
+
+ rpc_put_task(task);
out:
if (clp->cl_implid != NULL)
dprintk("NFS reply exchange_id: Server Implementation ID: "
clp->cl_implid->date.nseconds);
dprintk("NFS reply exchange_id: %d\n", status);
return status;
+
+ out_impl_id:
+ kfree(calldata->res.impl_id);
+ out_server_scope:
+ kfree(calldata->res.server_scope);
+ out_server_owner:
+ kfree(calldata->res.server_owner);
+ out_calldata:
+ kfree(calldata);
+ goto out;
}
/*
/* try SP4_MACH_CRED if krb5i/p */
if (authflavor == RPC_AUTH_GSS_KRB5I ||
authflavor == RPC_AUTH_GSS_KRB5P) {
- status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED);
+ status = _nfs4_proc_exchange_id(clp, cred, SP4_MACH_CRED, NULL);
if (!status)
return 0;
}
/* try SP4_NONE */
- return _nfs4_proc_exchange_id(clp, cred, SP4_NONE);
+ return _nfs4_proc_exchange_id(clp, cred, SP4_NONE, NULL);
+ }
+
+ /**
+ * nfs4_test_session_trunk
+ *
+ * This is an add_xprt_test() test function called from
+ * rpc_clnt_setup_test_and_add_xprt.
+ *
+ * The rpc_xprt_switch is referrenced by rpc_clnt_setup_test_and_add_xprt
+ * and is dereferrenced in nfs4_exchange_id_release
+ *
+ * Upon success, add the new transport to the rpc_clnt
+ *
+ * @clnt: struct rpc_clnt to get new transport
+ * @xprt: the rpc_xprt to test
+ * @data: call data for _nfs4_proc_exchange_id.
+ */
+ int nfs4_test_session_trunk(struct rpc_clnt *clnt, struct rpc_xprt *xprt,
+ void *data)
+ {
+ struct nfs4_add_xprt_data *adata = (struct nfs4_add_xprt_data *)data;
+ u32 sp4_how;
+
+ dprintk("--> %s try %s\n", __func__,
+ xprt->address_strings[RPC_DISPLAY_ADDR]);
+
+ sp4_how = (adata->clp->cl_sp4_flags == 0 ? SP4_NONE : SP4_MACH_CRED);
+
+ /* Test connection for session trunking. Async exchange_id call */
+ return _nfs4_proc_exchange_id(adata->clp, adata->cred, sp4_how, xprt);
}
+ EXPORT_SYMBOL_GPL(nfs4_test_session_trunk);
static int _nfs4_proc_destroy_clientid(struct nfs_client *clp,
struct rpc_cred *cred)
args->bc_attrs.max_resp_sz = max_bc_payload;
args->bc_attrs.max_resp_sz_cached = 0;
args->bc_attrs.max_ops = NFS4_MAX_BACK_CHANNEL_OPS;
- args->bc_attrs.max_reqs = NFS41_BC_MAX_CALLBACKS;
+ args->bc_attrs.max_reqs = min_t(unsigned short, max_session_cb_slots, 1);
dprintk("%s: Back Channel : max_rqst_sz=%u max_resp_sz=%u "
"max_resp_sz_cached=%u max_ops=%u max_reqs=%u\n",
return -EINVAL;
if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached)
return -EINVAL;
- /* These would render the backchannel useless: */
- if (rcvd->max_ops != sent->max_ops)
+ if (rcvd->max_ops > sent->max_ops)
return -EINVAL;
- if (rcvd->max_reqs != sent->max_reqs)
+ if (rcvd->max_reqs > sent->max_reqs)
return -EINVAL;
out:
return 0;
case -NFS4ERR_RECALLCONFLICT:
status = -ERECALLCONFLICT;
break;
+ case -NFS4ERR_DELEG_REVOKED:
+ case -NFS4ERR_ADMIN_REVOKED:
case -NFS4ERR_EXPIRED:
case -NFS4ERR_BAD_STATEID:
exception->timeout = 0;
&lgp->args.ctx->state->stateid)) {
spin_unlock(&inode->i_lock);
exception->state = lgp->args.ctx->state;
+ exception->stateid = &lgp->args.stateid;
break;
}
return -res.status;
}
+ static void nfs4_handle_delay_or_session_error(struct nfs_server *server,
+ int err, struct nfs4_exception *exception)
+ {
+ exception->retry = 0;
+ switch(err) {
+ case -NFS4ERR_DELAY:
+ case -NFS4ERR_RETRY_UNCACHED_REP:
+ nfs4_handle_exception(server, err, exception);
+ break;
+ case -NFS4ERR_BADSESSION:
+ case -NFS4ERR_BADSLOT:
+ case -NFS4ERR_BAD_HIGH_SLOT:
+ case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+ case -NFS4ERR_DEADSESSION:
+ nfs4_do_handle_exception(server, err, exception);
+ }
+ }
+
/**
* nfs41_test_stateid - perform a TEST_STATEID operation
*
int err;
do {
err = _nfs41_test_stateid(server, stateid, cred);
- if (err != -NFS4ERR_DELAY)
- break;
- nfs4_handle_exception(server, err, &exception);
+ nfs4_handle_delay_or_session_error(server, err, &exception);
} while (exception.retry);
return err;
}
};
static struct rpc_task *_nfs41_free_stateid(struct nfs_server *server,
- nfs4_stateid *stateid,
+ const nfs4_stateid *stateid,
struct rpc_cred *cred,
bool privileged)
{
msg.rpc_argp = &data->args;
msg.rpc_resp = &data->res;
- nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 0);
+ nfs4_init_sequence(&data->args.seq_args, &data->res.seq_res, 1);
if (privileged)
nfs4_set_sequence_privileged(&data->args.seq_args);
* @server: server / transport on which to perform the operation
* @stateid: state ID to release
* @cred: credential
+ * @is_recovery: set to true if this call needs to be privileged
*
- * Returns NFS_OK if the server freed "stateid". Otherwise a
- * negative NFS4ERR value is returned.
+ * Note: this function is always asynchronous.
*/
static int nfs41_free_stateid(struct nfs_server *server,
- nfs4_stateid *stateid,
- struct rpc_cred *cred)
+ const nfs4_stateid *stateid,
+ struct rpc_cred *cred,
+ bool is_recovery)
{
struct rpc_task *task;
- int ret;
- task = _nfs41_free_stateid(server, stateid, cred, true);
+ task = _nfs41_free_stateid(server, stateid, cred, is_recovery);
if (IS_ERR(task))
return PTR_ERR(task);
- ret = rpc_wait_for_completion_task(task);
- if (!ret)
- ret = task->tk_status;
rpc_put_task(task);
- return ret;
+ return 0;
}
static void
nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
{
- struct rpc_task *task;
struct rpc_cred *cred = lsp->ls_state->owner->so_cred;
- task = _nfs41_free_stateid(server, &lsp->ls_stateid, cred, false);
+ nfs41_free_stateid(server, &lsp->ls_stateid, cred, false);
nfs4_free_lock_state(server, lsp);
- if (IS_ERR(task))
- return;
- rpc_put_task(task);
}
static bool nfs41_match_stateid(const nfs4_stateid *s1,
.match_stateid = nfs4_match_stateid,
.find_root_sec = nfs4_find_root_sec,
.free_lock_state = nfs4_release_lockowner,
+ .test_and_free_expired = nfs40_test_and_free_expired_stateid,
.alloc_seqid = nfs_alloc_seqid,
.call_sync_ops = &nfs40_call_sync_ops,
.reboot_recovery_ops = &nfs40_reboot_recovery_ops,
.match_stateid = nfs41_match_stateid,
.find_root_sec = nfs41_find_root_sec,
.free_lock_state = nfs41_free_lock_state,
+ .test_and_free_expired = nfs41_test_and_free_expired_stateid,
.alloc_seqid = nfs_alloc_no_seqid,
+ .session_trunk = nfs4_test_session_trunk,
.call_sync_ops = &nfs41_call_sync_ops,
.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
.find_root_sec = nfs41_find_root_sec,
.free_lock_state = nfs41_free_lock_state,
.call_sync_ops = &nfs41_call_sync_ops,
+ .test_and_free_expired = nfs41_test_and_free_expired_stateid,
.alloc_seqid = nfs_alloc_no_seqid,
+ .session_trunk = nfs4_test_session_trunk,
.reboot_recovery_ops = &nfs41_reboot_recovery_ops,
.nograce_recovery_ops = &nfs41_nograce_recovery_ops,
.state_renewal_ops = &nfs41_state_renewal_ops,
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
- .getxattr = generic_getxattr,
- .setxattr = generic_setxattr,
.listxattr = nfs4_listxattr,
- .removexattr = generic_removexattr,
};
static const struct inode_operations nfs4_file_inode_operations = {
.permission = nfs_permission,
.getattr = nfs_getattr,
.setattr = nfs_setattr,
- .getxattr = generic_getxattr,
- .setxattr = generic_setxattr,
.listxattr = nfs4_listxattr,
- .removexattr = generic_removexattr,
};
const struct nfs_rpc_ops nfs_v4_clientops = {
wc->status, wc->vendor_err);
}
- static void
- rpcrdma_receive_worker(struct work_struct *work)
- {
- struct rpcrdma_rep *rep =
- container_of(work, struct rpcrdma_rep, rr_work);
-
- rpcrdma_reply_handler(rep);
- }
-
/* Perform basic sanity checking to avoid using garbage
* to update the credit grant value.
*/
}
/**
- * rpcrdma_receive_wc - Invoked by RDMA provider for each polled Receive WC
+ * rpcrdma_wc_receive - Invoked by RDMA provider for each polled Receive WC
* @cq: completion queue (ignored)
* @wc: completed WR
*
*/
static void
- rpcrdma_receive_wc(struct ib_cq *cq, struct ib_wc *wc)
+ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc)
{
struct ib_cqe *cqe = wc->wr_cqe;
struct rpcrdma_rep *rep = container_of(cqe, struct rpcrdma_rep,
__func__, rep, wc->byte_len);
rep->rr_len = wc->byte_len;
+ rep->rr_wc_flags = wc->wc_flags;
+ rep->rr_inv_rkey = wc->ex.invalidate_rkey;
+
ib_dma_sync_single_for_cpu(rep->rr_device,
rdmab_addr(rep->rr_rdmabuf),
rep->rr_len, DMA_FROM_DEVICE);
goto out_schedule;
}
+ static void
+ rpcrdma_update_connect_private(struct rpcrdma_xprt *r_xprt,
+ struct rdma_conn_param *param)
+ {
+ struct rpcrdma_create_data_internal *cdata = &r_xprt->rx_data;
+ const struct rpcrdma_connect_private *pmsg = param->private_data;
+ unsigned int rsize, wsize;
+
+ /* Default settings for RPC-over-RDMA Version One */
+ r_xprt->rx_ia.ri_reminv_expected = false;
+ rsize = RPCRDMA_V1_DEF_INLINE_SIZE;
+ wsize = RPCRDMA_V1_DEF_INLINE_SIZE;
+
+ if (pmsg &&
+ pmsg->cp_magic == rpcrdma_cmp_magic &&
+ pmsg->cp_version == RPCRDMA_CMP_VERSION) {
+ r_xprt->rx_ia.ri_reminv_expected = true;
+ rsize = rpcrdma_decode_buffer_size(pmsg->cp_send_size);
+ wsize = rpcrdma_decode_buffer_size(pmsg->cp_recv_size);
+ }
+
+ if (rsize < cdata->inline_rsize)
+ cdata->inline_rsize = rsize;
+ if (wsize < cdata->inline_wsize)
+ cdata->inline_wsize = wsize;
+ pr_info("rpcrdma: max send %u, max recv %u\n",
+ cdata->inline_wsize, cdata->inline_rsize);
+ rpcrdma_set_max_header_sizes(r_xprt);
+ }
+
static int
rpcrdma_conn_upcall(struct rdma_cm_id *id, struct rdma_cm_event *event)
{
" (%d initiator)\n",
__func__, attr->max_dest_rd_atomic,
attr->max_rd_atomic);
+ rpcrdma_update_connect_private(xprt, &event->param.conn);
goto connected;
case RDMA_CM_EVENT_CONNECT_ERROR:
connstate = -ENOTCONN;
}
ia->ri_device = ia->ri_id->device;
- ia->ri_pd = ib_alloc_pd(ia->ri_device);
+ ia->ri_pd = ib_alloc_pd(ia->ri_device, 0);
if (IS_ERR(ia->ri_pd)) {
rc = PTR_ERR(ia->ri_pd);
pr_err("rpcrdma: ib_alloc_pd() returned %d\n", rc);
rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
struct rpcrdma_create_data_internal *cdata)
{
+ struct rpcrdma_connect_private *pmsg = &ep->rep_cm_private;
struct ib_cq *sendcq, *recvcq;
unsigned int max_qp_wr;
int rc;
- if (ia->ri_device->attrs.max_sge < RPCRDMA_MAX_IOVS) {
+ if (ia->ri_device->attrs.max_sge < RPCRDMA_MAX_SEND_SGES) {
dprintk("RPC: %s: insufficient sge's available\n",
__func__);
return -ENOMEM;
ep->rep_attr.cap.max_recv_wr = cdata->max_requests;
ep->rep_attr.cap.max_recv_wr += RPCRDMA_BACKWARD_WRS;
ep->rep_attr.cap.max_recv_wr += 1; /* drain cqe */
- ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_IOVS;
+ ep->rep_attr.cap.max_send_sge = RPCRDMA_MAX_SEND_SGES;
ep->rep_attr.cap.max_recv_sge = 1;
ep->rep_attr.cap.max_inline_data = 0;
ep->rep_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
/* Initialize cma parameters */
memset(&ep->rep_remote_cma, 0, sizeof(ep->rep_remote_cma));
- /* RPC/RDMA does not use private data */
- ep->rep_remote_cma.private_data = NULL;
- ep->rep_remote_cma.private_data_len = 0;
+ /* Prepare RDMA-CM private message */
+ pmsg->cp_magic = rpcrdma_cmp_magic;
+ pmsg->cp_version = RPCRDMA_CMP_VERSION;
+ pmsg->cp_flags |= ia->ri_ops->ro_send_w_inv_ok;
+ pmsg->cp_send_size = rpcrdma_encode_buffer_size(cdata->inline_wsize);
+ pmsg->cp_recv_size = rpcrdma_encode_buffer_size(cdata->inline_rsize);
+ ep->rep_remote_cma.private_data = pmsg;
+ ep->rep_remote_cma.private_data_len = sizeof(*pmsg);
/* Client offers RDMA Read but does not initiate */
ep->rep_remote_cma.initiator_depth = 0;
req->rl_cqe.done = rpcrdma_wc_send;
req->rl_buffer = &r_xprt->rx_buf;
INIT_LIST_HEAD(&req->rl_registered);
+ req->rl_send_wr.next = NULL;
+ req->rl_send_wr.wr_cqe = &req->rl_cqe;
+ req->rl_send_wr.sg_list = req->rl_send_sge;
+ req->rl_send_wr.opcode = IB_WR_SEND;
return req;
}
if (rep == NULL)
goto out;
- rep->rr_rdmabuf = rpcrdma_alloc_regbuf(ia, cdata->inline_rsize,
- GFP_KERNEL);
+ rep->rr_rdmabuf = rpcrdma_alloc_regbuf(cdata->inline_rsize,
+ DMA_FROM_DEVICE, GFP_KERNEL);
if (IS_ERR(rep->rr_rdmabuf)) {
rc = PTR_ERR(rep->rr_rdmabuf);
goto out_free;
}
rep->rr_device = ia->ri_device;
- rep->rr_cqe.done = rpcrdma_receive_wc;
+ rep->rr_cqe.done = rpcrdma_wc_receive;
rep->rr_rxprt = r_xprt;
- INIT_WORK(&rep->rr_work, rpcrdma_receive_worker);
+ INIT_WORK(&rep->rr_work, rpcrdma_reply_handler);
+ rep->rr_recv_wr.next = NULL;
+ rep->rr_recv_wr.wr_cqe = &rep->rr_cqe;
+ rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
+ rep->rr_recv_wr.num_sge = 1;
return rep;
out_free:
}
static void
- rpcrdma_destroy_rep(struct rpcrdma_ia *ia, struct rpcrdma_rep *rep)
+ rpcrdma_destroy_rep(struct rpcrdma_rep *rep)
{
- rpcrdma_free_regbuf(ia, rep->rr_rdmabuf);
+ rpcrdma_free_regbuf(rep->rr_rdmabuf);
kfree(rep);
}
void
- rpcrdma_destroy_req(struct rpcrdma_ia *ia, struct rpcrdma_req *req)
+ rpcrdma_destroy_req(struct rpcrdma_req *req)
{
- rpcrdma_free_regbuf(ia, req->rl_sendbuf);
- rpcrdma_free_regbuf(ia, req->rl_rdmabuf);
+ rpcrdma_free_regbuf(req->rl_recvbuf);
+ rpcrdma_free_regbuf(req->rl_sendbuf);
+ rpcrdma_free_regbuf(req->rl_rdmabuf);
kfree(req);
}
void
rpcrdma_buffer_destroy(struct rpcrdma_buffer *buf)
{
- struct rpcrdma_ia *ia = rdmab_to_ia(buf);
-
cancel_delayed_work_sync(&buf->rb_recovery_worker);
while (!list_empty(&buf->rb_recv_bufs)) {
struct rpcrdma_rep *rep;
rep = rpcrdma_buffer_get_rep_locked(buf);
- rpcrdma_destroy_rep(ia, rep);
+ rpcrdma_destroy_rep(rep);
}
buf->rb_send_count = 0;
list_del(&req->rl_all);
spin_unlock(&buf->rb_reqslock);
- rpcrdma_destroy_req(ia, req);
+ rpcrdma_destroy_req(req);
spin_lock(&buf->rb_reqslock);
}
spin_unlock(&buf->rb_reqslock);
struct rpcrdma_buffer *buffers = req->rl_buffer;
struct rpcrdma_rep *rep = req->rl_reply;
- req->rl_niovs = 0;
+ req->rl_send_wr.num_sge = 0;
req->rl_reply = NULL;
spin_lock(&buffers->rb_lock);
spin_unlock(&buffers->rb_lock);
}
- /*
- * Wrappers for internal-use kmalloc memory registration, used by buffer code.
- */
-
/**
- * rpcrdma_alloc_regbuf - kmalloc and register memory for SEND/RECV buffers
- * @ia: controlling rpcrdma_ia
+ * rpcrdma_alloc_regbuf - allocate and DMA-map memory for SEND/RECV buffers
* @size: size of buffer to be allocated, in bytes
+ * @direction: direction of data movement
* @flags: GFP flags
*
- * Returns pointer to private header of an area of internally
- * registered memory, or an ERR_PTR. The registered buffer follows
- * the end of the private header.
+ * Returns an ERR_PTR, or a pointer to a regbuf, a buffer that
+ * can be persistently DMA-mapped for I/O.
*
* xprtrdma uses a regbuf for posting an outgoing RDMA SEND, or for
- * receiving the payload of RDMA RECV operations. regbufs are not
- * used for RDMA READ/WRITE operations, thus are registered only for
- * LOCAL access.
+ * receiving the payload of RDMA RECV operations. During Long Calls
+ * or Replies they may be registered externally via ro_map.
*/
struct rpcrdma_regbuf *
- rpcrdma_alloc_regbuf(struct rpcrdma_ia *ia, size_t size, gfp_t flags)
+ rpcrdma_alloc_regbuf(size_t size, enum dma_data_direction direction,
+ gfp_t flags)
{
struct rpcrdma_regbuf *rb;
- struct ib_sge *iov;
rb = kmalloc(sizeof(*rb) + size, flags);
if (rb == NULL)
- goto out;
+ return ERR_PTR(-ENOMEM);
- iov = &rb->rg_iov;
- iov->addr = ib_dma_map_single(ia->ri_device,
- (void *)rb->rg_base, size,
- DMA_BIDIRECTIONAL);
- if (ib_dma_mapping_error(ia->ri_device, iov->addr))
- goto out_free;
+ rb->rg_device = NULL;
+ rb->rg_direction = direction;
+ rb->rg_iov.length = size;
- iov->length = size;
- iov->lkey = ia->ri_pd->local_dma_lkey;
- rb->rg_size = size;
- rb->rg_owner = NULL;
return rb;
+ }
- out_free:
- kfree(rb);
- out:
- return ERR_PTR(-ENOMEM);
+ /**
+ * __rpcrdma_map_regbuf - DMA-map a regbuf
+ * @ia: controlling rpcrdma_ia
+ * @rb: regbuf to be mapped
+ */
+ bool
+ __rpcrdma_dma_map_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb)
+ {
+ if (rb->rg_direction == DMA_NONE)
+ return false;
+
+ rb->rg_iov.addr = ib_dma_map_single(ia->ri_device,
+ (void *)rb->rg_base,
+ rdmab_length(rb),
+ rb->rg_direction);
+ if (ib_dma_mapping_error(ia->ri_device, rdmab_addr(rb)))
+ return false;
+
+ rb->rg_device = ia->ri_device;
+ rb->rg_iov.lkey = ia->ri_pd->local_dma_lkey;
+ return true;
+ }
+
+ static void
+ rpcrdma_dma_unmap_regbuf(struct rpcrdma_regbuf *rb)
+ {
+ if (!rpcrdma_regbuf_is_mapped(rb))
+ return;
+
+ ib_dma_unmap_single(rb->rg_device, rdmab_addr(rb),
+ rdmab_length(rb), rb->rg_direction);
+ rb->rg_device = NULL;
}
/**
* rpcrdma_free_regbuf - deregister and free registered buffer
- * @ia: controlling rpcrdma_ia
* @rb: regbuf to be deregistered and freed
*/
void
- rpcrdma_free_regbuf(struct rpcrdma_ia *ia, struct rpcrdma_regbuf *rb)
+ rpcrdma_free_regbuf(struct rpcrdma_regbuf *rb)
{
- struct ib_sge *iov;
-
if (!rb)
return;
- iov = &rb->rg_iov;
- ib_dma_unmap_single(ia->ri_device,
- iov->addr, iov->length, DMA_BIDIRECTIONAL);
+ rpcrdma_dma_unmap_regbuf(rb);
kfree(rb);
}
struct rpcrdma_ep *ep,
struct rpcrdma_req *req)
{
- struct ib_device *device = ia->ri_device;
- struct ib_send_wr send_wr, *send_wr_fail;
- struct rpcrdma_rep *rep = req->rl_reply;
- struct ib_sge *iov = req->rl_send_iov;
- int i, rc;
+ struct ib_send_wr *send_wr = &req->rl_send_wr;
+ struct ib_send_wr *send_wr_fail;
+ int rc;
- if (rep) {
- rc = rpcrdma_ep_post_recv(ia, ep, rep);
+ if (req->rl_reply) {
+ rc = rpcrdma_ep_post_recv(ia, req->rl_reply);
if (rc)
return rc;
req->rl_reply = NULL;
}
- send_wr.next = NULL;
- send_wr.wr_cqe = &req->rl_cqe;
- send_wr.sg_list = iov;
- send_wr.num_sge = req->rl_niovs;
- send_wr.opcode = IB_WR_SEND;
-
- for (i = 0; i < send_wr.num_sge; i++)
- ib_dma_sync_single_for_device(device, iov[i].addr,
- iov[i].length, DMA_TO_DEVICE);
dprintk("RPC: %s: posting %d s/g entries\n",
- __func__, send_wr.num_sge);
+ __func__, send_wr->num_sge);
if (DECR_CQCOUNT(ep) > 0)
- send_wr.send_flags = 0;
+ send_wr->send_flags = 0;
else { /* Provider must take a send completion every now and then */
INIT_CQCOUNT(ep);
- send_wr.send_flags = IB_SEND_SIGNALED;
+ send_wr->send_flags = IB_SEND_SIGNALED;
}
- rc = ib_post_send(ia->ri_id->qp, &send_wr, &send_wr_fail);
+ rc = ib_post_send(ia->ri_id->qp, send_wr, &send_wr_fail);
if (rc)
goto out_postsend_err;
return 0;
return -ENOTCONN;
}
- /*
- * (Re)post a receive buffer.
- */
int
rpcrdma_ep_post_recv(struct rpcrdma_ia *ia,
- struct rpcrdma_ep *ep,
struct rpcrdma_rep *rep)
{
- struct ib_recv_wr recv_wr, *recv_wr_fail;
+ struct ib_recv_wr *recv_wr_fail;
int rc;
- recv_wr.next = NULL;
- recv_wr.wr_cqe = &rep->rr_cqe;
- recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov;
- recv_wr.num_sge = 1;
-
- ib_dma_sync_single_for_cpu(ia->ri_device,
- rdmab_addr(rep->rr_rdmabuf),
- rdmab_length(rep->rr_rdmabuf),
- DMA_BIDIRECTIONAL);
-
- rc = ib_post_recv(ia->ri_id->qp, &recv_wr, &recv_wr_fail);
+ if (!rpcrdma_dma_map_regbuf(ia, rep->rr_rdmabuf))
+ goto out_map;
+ rc = ib_post_recv(ia->ri_id->qp, &rep->rr_recv_wr, &recv_wr_fail);
if (rc)
goto out_postrecv;
return 0;
+ out_map:
+ pr_err("rpcrdma: failed to DMA map the Receive buffer\n");
+ return -EIO;
+
out_postrecv:
pr_err("rpcrdma: ib_post_recv returned %i\n", rc);
return -ENOTCONN;
{
struct rpcrdma_buffer *buffers = &r_xprt->rx_buf;
struct rpcrdma_ia *ia = &r_xprt->rx_ia;
- struct rpcrdma_ep *ep = &r_xprt->rx_ep;
struct rpcrdma_rep *rep;
int rc;
rep = rpcrdma_buffer_get_rep_locked(buffers);
spin_unlock(&buffers->rb_lock);
- rc = rpcrdma_ep_post_recv(ia, ep, rep);
+ rc = rpcrdma_ep_post_recv(ia, rep);
if (rc)
goto out_rc;
}